Exploiting Cross-Sentence Context for Neural Machine Translation

Wang, Longyue; Tu, Zhaopeng; Way, Andy; Liu, Qun

doi:10.18653/v1/d17-1301

Cited by 164 publications

(221 citation statements)

References 20 publications

Supporting

Mentioning

217

Contrasting

Order By: Relevance

“…Encoding Discourse-Level Context Hierarchical structure networks are usually used for modelling discourse context on various natural language processing tasks such query suggestion (Sordoni et al, 2015), dialogue modeling (Serban et al, 2016) and MT (Wang et al, 2017). Therefore, we employ hierarchical encoder (Wang et al, 2017) to encoder discourse-level context for NMT. More specifically, we use the previous K source sentences X = {x −K , .…”

Section: Discourse-aware Zp Predictionmentioning

confidence: 99%

“…Inspired by these findings, we exploit intersentential context to further improve ZP prediction and thus translation. Concretely, we employ hierarchical neural networks (Sordoni et al, 2015;Wang et al, 2017) to summarize the context of previous sentences in a text, which is integrated to the joint model for ZP prediction.…”

Section: Introductionmentioning

confidence: 99%

“…http://www.opensubtitles.org.5 We followedWang et al (2017) andTu et al (2018) to use 3 previous sentences as discourse context.…”

mentioning

confidence: 99%

See 2 more Smart Citations

One Model to Learn Both: Zero Pronoun Prediction and Translation

Wang¹,

Tu²,

Wang³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

Zero pronouns (ZPs) are frequently omitted in pro-drop languages, but should be recalled in non-pro-drop languages. This discourse phenomenon poses a significant challenge for machine translation (MT) when translating texts from pro-drop to non-pro-drop languages. In this paper, we propose a unified and discourseaware ZP translation approach for neural MT models. Specifically, we jointly learn to predict and translate ZPs in an end-to-end manner, allowing both components to interact with each other. In addition, we employ hierarchical neural networks to exploit discourse-level context, which is beneficial for ZP prediction and thus translation. Experimental results on both Chinese⇒English and Japanese⇒English data show that our approach significantly and accumulatively improves both translation performance and ZP prediction accuracy over not only baseline but also previous works using external ZP prediction models. Extensive analyses confirm that the performance improvement comes from the alleviation of different kinds of errors especially caused by subjective ZPs.

show abstract

Section: Discourse-aware Zp Predictionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

One Model to Learn Both: Zero Pronoun Prediction and Translation

Wang¹,

Tu²,

Wang³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

show abstract

“…While sentence-level evaluation may be good enough when evaluating MT systems of relatively low quality, we hypothesise that with additional context, raters will be able to make more nuanced quality assessments, and will also reward translations that show more textual cohesion and coherence. We believe that this aspect should be considered in evaluation, especially when making claims about human-machine parity, since human translators can and do take inter-sentential context into account (Voigt & Jurafsky, 2012;Wang et al, 2017).…”

Section: Linguistic Contextmentioning

confidence: 99%

A Set of Recommendations for Assessing Human–Machine Parity in Language Translation

Läubli

Castilho

Neubig

et al. 2020

jair

View full text Add to dashboard Cite

The quality of machine translation has increased remarkably over the past years, to the degree that it was found to be indistinguishable from professional human translation in a number of empirical investigations. We reassess Hassan et al.'s 2018 investigation into Chinese to English news translation, showing that the finding of human-machine parity was owed to weaknesses in the evaluation design-which is currently considered best practice in the field. We show that the professional human translations contained significantly fewer errors, and that perceived quality in human evaluation depends on the choice of raters, the availability of linguistic context, and the creation of reference translations. Our results call for revisiting current best practices to assess strong machine translation systems in general and human-machine parity in particular, for which we offer a set of recommendations based on our empirical findings.

show abstract

“…Intuitively, to generate better translation of the entire text, the model deserves considering the cross-sentence connections and dependencies, generating discourse coherent translations. Towards this demand, most previous work (Wang et al 2017;Voita et al 2018) proposed to explore additional context, generally is certain preceding adjacent sentences, to reinforce the model. However, the major goal of these models is still the quality of individual sentence while not Copyright c 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org).…”

Section: Introductionmentioning

confidence: 99%

Modeling Coherence for Discourse Neural Machine Translation

Xiong

et al. 2019

AAAI

View full text Add to dashboard Cite

Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which affects the coherence of the text. In this paper, we propose to use discourse context and reward to refine the translation quality from the discourse perspective. In particular, we generate the translation of individual sentences at first. Next, we deliberate the preliminary produced translations, and train the model to learn the policy that produces discourse coherent text by a reward teacher. Practical results on multiple discourse test datasets indicate that our model significantly improves the translation quality over the state-of-the-art baseline system by +1.23 BLEU score. Moreover, our model generates more discourse coherent text and obtains +2.2 BLEU improvements when evaluated by discourse metrics.

show abstract

Exploiting Cross-Sentence Context for Neural Machine Translation

Cited by 164 publications

References 20 publications

One Model to Learn Both: Zero Pronoun Prediction and Translation

One Model to Learn Both: Zero Pronoun Prediction and Translation

A Set of Recommendations for Assessing Human–Machine Parity in Language Translation

Modeling Coherence for Discourse Neural Machine Translation

Contact Info

Product

Resources

About